Optimization of the Model Predictive Control Meta-Parameters Through Reinforcement Learning

by   Eivind Bøhn, et al.

Model predictive control (MPC) is increasingly being considered for control of fast systems and embedded applications. However, the MPC has some significant challenges for such systems. Its high computational complexity results in high power consumption from the control algorithm, which could account for a significant share of the energy resources in battery-powered embedded systems. The MPC parameters must be tuned, which is largely a trial-and-error process that affects the control performance, the robustness and the computational complexity of the controller to a high degree. In this paper, we propose a novel framework in which any parameter of the control algorithm can be jointly tuned using reinforcement learning(RL), with the goal of simultaneously optimizing the control performance and the power usage of the control algorithm. We propose the novel idea of optimizing the meta-parameters of MPCwith RL, i.e. parameters affecting the structure of the MPCproblem as opposed to the solution to a given problem. Our control algorithm is based on an event-triggered MPC where we learn when the MPC should be re-computed, and a dual mode MPC and linear state feedback control law applied in between MPC computations. We formulate a novel mixture-distribution policy and show that with joint optimization we achieve improvements that do not present themselves when optimizing the same parameters in isolation. We demonstrate our framework on the inverted pendulum control task, reducing the total computation time of the control system by 36 over the best-performing MPC baseline.


page 1

page 11


Optimization of the Model Predictive Control Update Interval Using Reinforcement Learning

In control applications there is often a compromise that needs to be mad...

Infusing model predictive control into meta-reinforcement learning for mobile robots in dynamic environments

The successful operation of mobile robots requires them to rapidly adapt...

Reinforcement Learning of the Prediction Horizon in Model Predictive Control

Model predictive control (MPC) is a powerful trajectory optimization con...

Coalition Control Model: A Dynamic Resource Distribution Method Based on Model Predicative Control

Optimization of resource distribution has been a challenging topic in cu...

Learning-based MPC from Big Data Using Reinforcement Learning

This paper presents an approach for learning Model Predictive Control (M...

Haptic Teleoperation of High-dimensional Robotic Systems Using a Feedback MPC Framework

Model Predictive Control (MPC) schemes have proven their efficiency in c...

A model predictive control (MPC)-integrated multiphase immersed boundary (IB) framework for simulating wave energy converters (WECs)

In this work, we present a novel MPC-integrated multiphase IB framework ...

Please sign up or login with your details

Forgot password? Click here to reset